Borrowing it
Nothing to install: this file belongs to xi-zhao/OpenQuantum. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/xi-zhao/OpenQuantum/main/.agents/skills/quantum-information-audit/SKILL.mdgit clone --depth 1 https://github.com/xi-zhao/OpenQuantumWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/xi-zhao/openquantum/quantum-information-audit)<a href="https://agentmods.dev/skills/xi-zhao/openquantum/quantum-information-audit"><img src="https://agentmods.dev/badge/skills/xi-zhao/openquantum/quantum-information-audit.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00101 | $0.00749 |
| Opus 5 | $0.00051 | $0.00375 |
| Sonnet 5 | $0.00020 | $0.00150 |
| Haiku 4.5 | $0.00010 | $0.00075 |
Grade A, and why
quantum-information-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
量子信息审计
核心边界
本能力只审计用户已经给出的密度矩阵。核心对象是版本化的审计请求：复矩阵的实部/虚部、子系统维数，以及需要做部分转置的子系统索引。
toqitoMCP-exposed Tool 产生数值事实。- OpenQuantum Validator 用独立 JavaScript 实现重算迹、Hermiticity、正半定性、纯度、部分转置谱和 negativity。
- MCP-exposed Tool 的结果标记
observations_available，不等于最终科学验收。只有物化 Result Package 并核对 Session Event Log 来源链后，才可能形成最终 Acceptance。
工作流
- 确认矩阵总维数等于
subsystemDimensions的乘积，且不超过 16。 - 明确
transposeSubsystems采用从 0 开始的子系统索引，并且是非空真子集。 - 调用
audit_density_matrix。复矩阵用matrixReal和可选的matrixImag表示；未给虚部时按全零处理。主动作加载固定环境并返回packageVersion，首次调用可能下载依赖并写入工作区环境，无需单独检查运行时。 - 分栏报告实际包版本及：
- toqito 事实；
- 独立 Validator observations；
- 失败、不检查项和适用范围。
- 确认
tool/result是否包含acceptance_available与 Result Commit；只有可信 Host Plugin 通过 内部 Scientific Result Adapter 进入 Materializer，并完成物化、重读和校验时，才能按 central Acceptance Builder 推导的状态报告最终验收。 - 不把 negativity 写成普适的纠缠分类结论；它只对应本次指定的二分和部分转置判据。
必须保持的规则
- 不提交云任务或真实量子硬件任务。
- 不接受调用方自定义容差；容差由版本化 Acceptance Profile 固定。
provenance.complete=not_checked时不得宣称科学验收通过。- 不凭 MCP-exposed Tool 的文本内容自行推断
passed；最终状态必须来自 Harness 物化后的 Acceptance Report。 - 工具失败、科学 observation 失败、来源链未检查是三种不同状态。
- 不从分子结构、实验层析数据或任意量子信道自动推导密度矩阵。
示例
Bell 态 |Phi+><Phi+| 使用 subsystemDimensions=[2,2]、transposeSubsystems=[0]。预期纯度为 1、部分转置最小本征值为 -0.5、negativity 为 0.5；仍需以实际工具事实和 Validator observations 为准。
What ships with it
16 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- acceptance-profiles/density-matrix-audit-v1.json 2.5 KB
- agents/openai.yaml 455 B
- artifacts/state-analysis.schema.json 2.1 KB
- artifacts/validation-bundle.schema.json 941 B
- capability.yaml 3.2 KB
- evals/run-evals.mjs 5.9 KB runs code
- evals/suite.json 1.2 KB
- inputs/request.schema.json 1.2 KB
- mcp/bridge.py 6.0 KB runs code
- mcp/server.mjs 6.3 KB runs code
- pyproject.toml 165 B
- reproduction-profiles/local-toqito-js-replay-v1.json 1.8 KB
- test/mcp.test.mjs 5.6 KB runs code
- uv.lock 231 KB
- validators/state-math.mjs 10 KB runs code
- validators/validate-state-analysis.mjs 11 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago Changed · -1 lines f1c3a580d446
- 8d ago First seen · 44 lines · 101 tokens per session scan A 056f71a0dbc7
quantum-information-audit is a skill published in the GitHub repository xi-zhao/OpenQuantum (48 stars, last pushed yesterday), licensed MIT. It adds 101 tokens to every session and 749 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
academic-research
Search academic papers, scholarly articles, and research publications through SandBase. Use when asked for literature review, academic citations, scholarly research, paper discovery, or scientific evidence gathering.
academic-trend-research
Research emerging academic trends by combining scholarly databases, web sources, and news to identify rising research areas, breakthrough papers, and shifting scientific consensus. Ideal for R&D teams tracking frontier science.
alexandria
Reach for this when a research question needs cited sources across academic papers, public domain books, legal records, government archives, security advisories, news, or developer documentation. Alexandria is an MCP server backed by 152 public digital libraries; use it whenever an answer should point at real…
memory-search-mcp
Long-term memory and context retrieval for AI agents. Semantic search across conversation history with care-weighted relevance.
ml-experiment-review
Use this skill when reviewing an ML experiment, benchmark, ablation, or training run.
noodle-biomedical-literature-discovery
Find, inspect, compare, and traverse public biomedical research literature. Use for PubMed or scholarly paper search, publication details, PMID/DOI/PMCID lookup, related papers, citation paths, semantic literature neighborhoods, corpus coverage, or questions asking what research exists about a gene, variant…